FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913304943> ?p ?o ?g. }

• W2913304943 abstract "Classification is a fundamental problem in the field of statistical machine learning. In classification, issues of nonlinear separability and multimodality are frequently encountered even in relatively small data sets. Distance-based classifiers, such as the nearest neighbour (NN) classifier which classifies a new instance by computing distances between this instance and the training instances, have been found useful to deal with nonlinear separability and multimodality. However, the performance of distance-based classifiers heavily depends on the underlying distance metric, so it is valuable to study metric learning, which enables the algorithms to automatically learn a suitable metric from available data. In this thesis, I discuss the topic of metric learning with Lipschitz continuous functions. The classifiers are restricted to have certain Lipschitz continuous properties, so that the performance guarantee of classifiers, which could be described by probably approximately correct (PAC) learning bounds, would be obtained. In Chapter 2, I propose a framework in which the metric would be learned with the criterion of large margin ratio. Both inter-class margin and intra-class dispersion are considered in the criterion, so as to enhance the generalisation ability of classifiers. Some well-known metric learning algorithms can be shown as special cases of the proposed framework. In Chapter 3, I suggest that multiple local metrics would be learned to deal with multimodality problems. I define an intuitive distance with local metrics and influential regions, and subsequently propose a novel local metric learning method for distance-based classification. The key intuition is to partition the metric space into influential regions and a background region, and then regulate the effectiveness of each local metric to be within the related influential regions. In Chapter 4, metric learning with instance extraction (MLIE) is discussed. A big drawback of the NN classifier is that it needs to store all training instances, hence it suffers from problems of storage and computation. Therefore, I propose an algorithm to extract a small number of useful instances, which would reduce the costs of storage as well as the computation costs during the test stage. Furthermore, the proposed instance extraction method could be understood as an elegant way to do local linear classification, i.e. simultaneously learn the positions of local areas and the linear classifiers inside the local areas. In Chapter 5, based on an algorithm-dependent PAC bound, another algorithm of MLIE is proposed. Besides the Lipschitz continuous requirement with respect to the parameter, the Lipschitz continuous requirement with respect to the gradient of parameter will also be considered. Therefore, smooth classifiers and smooth loss functions are proposed in this chapter. The classifiers proposed in Chapter 2 and Chapter 3 have bounded values of lip(h x) with a PAC bound, where lip(h x) denotes the Lipschitz constant of the function with respect to the input space X. The classifiers proposed in Chapter 4 enjoys the bounded value of lip(h ) with a tighter PAC bound, where lip(h ) denotes the Lipschitz constant of the function with respect to the input space . In Chapter 5, to consider the property of the optimisation algorithm simultaneously, an algorithm-dependent PAC bound based on Lipschitz smoothness is derived." @default.
• W2913304943 created "2019-02-21" @default.
• W2913304943 creator A5023352537 @default.
• W2913304943 date "2019-01-28" @default.
• W2913304943 modified "2023-09-28" @default.
• W2913304943 title "Metric learning with Lipschitz continuous functions" @default.
• W2913304943 cites W1481757049 @default.
• W2913304943 cites W1496314943 @default.
• W2913304943 cites W1967073510 @default.
• W2913304943 cites W2019363670 @default.
• W2913304943 cites W2046901748 @default.
• W2913304943 cites W2063135797 @default.
• W2913304943 cites W2084544490 @default.
• W2913304943 cites W2086924628 @default.
• W2913304943 cites W2103959632 @default.
• W2913304943 cites W2104752854 @default.
• W2913304943 cites W2106053110 @default.
• W2913304943 cites W2116731705 @default.
• W2913304943 cites W2117154949 @default.
• W2913304943 cites W2118393783 @default.
• W2913304943 cites W2129156852 @default.
• W2913304943 cites W2133126147 @default.
• W2913304943 cites W2138457014 @default.
• W2913304943 cites W2140376886 @default.
• W2913304943 cites W2144935315 @default.
• W2913304943 cites W2145339207 @default.
• W2913304943 cites W2162828817 @default.
• W2913304943 cites W2169495281 @default.
• W2913304943 cites W2174144271 @default.
• W2913304943 cites W2189508540 @default.
• W2913304943 cites W2212197243 @default.
• W2913304943 cites W2215054329 @default.
• W2913304943 cites W2287985126 @default.
• W2913304943 cites W2512601085 @default.
• W2913304943 cites W2553303224 @default.
• W2913304943 cites W2586258914 @default.
• W2913304943 cites W2736970300 @default.
• W2913304943 cites W2743192842 @default.
• W2913304943 cites W2781787017 @default.
• W2913304943 cites W2782903244 @default.
• W2913304943 cites W2783863635 @default.
• W2913304943 cites W2785494456 @default.
• W2913304943 cites W2913535645 @default.
• W2913304943 cites W2963664410 @default.
• W2913304943 cites W2963794891 @default.
• W2913304943 cites W603776396 @default.
• W2913304943 cites W607505555 @default.
• W2913304943 hasPublicationYear "2019" @default.
• W2913304943 type Work @default.
• W2913304943 sameAs 2913304943 @default.
• W2913304943 citedByCount "0" @default.
• W2913304943 crossrefType "dissertation" @default.
• W2913304943 hasAuthorship W2913304943A5023352537 @default.
• W2913304943 hasConcept C114614502 @default.
• W2913304943 hasConcept C118615104 @default.
• W2913304943 hasConcept C119857082 @default.
• W2913304943 hasConcept C134306372 @default.
• W2913304943 hasConcept C153180895 @default.
• W2913304943 hasConcept C154945302 @default.
• W2913304943 hasConcept C162324750 @default.
• W2913304943 hasConcept C176217482 @default.
• W2913304943 hasConcept C198043062 @default.
• W2913304943 hasConcept C21547014 @default.
• W2913304943 hasConcept C22324862 @default.
• W2913304943 hasConcept C33923547 @default.
• W2913304943 hasConcept C41008148 @default.
• W2913304943 hasConcept C42812 @default.
• W2913304943 hasConcept C774472 @default.
• W2913304943 hasConcept C95623464 @default.
• W2913304943 hasConceptScore W2913304943C114614502 @default.
• W2913304943 hasConceptScore W2913304943C118615104 @default.
• W2913304943 hasConceptScore W2913304943C119857082 @default.
• W2913304943 hasConceptScore W2913304943C134306372 @default.
• W2913304943 hasConceptScore W2913304943C153180895 @default.
• W2913304943 hasConceptScore W2913304943C154945302 @default.
• W2913304943 hasConceptScore W2913304943C162324750 @default.
• W2913304943 hasConceptScore W2913304943C176217482 @default.
• W2913304943 hasConceptScore W2913304943C198043062 @default.
• W2913304943 hasConceptScore W2913304943C21547014 @default.
• W2913304943 hasConceptScore W2913304943C22324862 @default.
• W2913304943 hasConceptScore W2913304943C33923547 @default.
• W2913304943 hasConceptScore W2913304943C41008148 @default.
• W2913304943 hasConceptScore W2913304943C42812 @default.
• W2913304943 hasConceptScore W2913304943C774472 @default.
• W2913304943 hasConceptScore W2913304943C95623464 @default.
• W2913304943 hasLocation W29133049431 @default.
• W2913304943 hasOpenAccess W2913304943 @default.
• W2913304943 hasPrimaryLocation W29133049431 @default.
• W2913304943 hasRelatedWork W1536270631 @default.
• W2913304943 hasRelatedWork W1572401054 @default.
• W2913304943 hasRelatedWork W1588148453 @default.
• W2913304943 hasRelatedWork W1607958634 @default.
• W2913304943 hasRelatedWork W1767625659 @default.
• W2913304943 hasRelatedWork W1964928737 @default.
• W2913304943 hasRelatedWork W2015430519 @default.
• W2913304943 hasRelatedWork W2075447277 @default.
• W2913304943 hasRelatedWork W2104752854 @default.
• W2913304943 hasRelatedWork W2201177080 @default.
• W2913304943 hasRelatedWork W2566216799 @default.
• W2913304943 hasRelatedWork W2787393537 @default.

• next